Quality control and filtering results from cellranger

Sample info and environment setup

PRJNA732205

setwd("/media/jacopo/Elements/re_align/MM/PRJNA732205/SAMN19314092/SRR14629352/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree 
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)

Load and process cellranger data

Load and do the QC for the cellranger data

#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial, 
    "\nNumber of genes:",  dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 13291 
## Number of genes: 36601

Quality Control

Empty cells were already filtered, check for % mt RNA and death markers:

# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 15
max_counts = 30000



# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt"))  + geom_hline(yintercept=mt_rna, linetype = "dotted")

plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1 

plot2

##  cells retained by mt RNA content ( 15 %): 5640 
##  percentage of retained cells: 42.43 %
## cells retained by counts ( 30000 ): 5637 
##  percentage of retained cells: 42.41 %

Check the distribution of the cells with low counts and control death markers:

min_counts = 600


hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")

hist(dat@meta.data$nCount_RNA, breaks = 1000, xlab = "Counts", xlim = c(0,5000))

hist(dat@meta.data$nCount_RNA, breaks = 10000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)

The evident peak of cells with < 200 counts could contain dying cells.

# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)

# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)

# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)

# Print the most highly expressed genes
head(meanCounts, 30)
##    MALAT1   IGLV2-8    MT-CO2     RPS27    EEF1A1    MT-ND3    MT-CO3    MT-CO1 
## 13.947578  7.215112  5.062545  3.020607  3.017715  2.901302  2.579176  2.534707 
##     RPL41      CD74     RPLP1     RPL10     RPL34     RPS12      RPS8     RPL39 
##  2.272957  2.145336  2.106291  2.104483  2.071222  2.053145  2.019523  1.949747 
##    MT-CYB     RPL30   MT-ND4L     RPL32     RPS23    RPS27A     RPL13     RPL11 
##  1.926970  1.895879  1.891179  1.820318  1.642805  1.619306  1.591829  1.528200 
##     RPS28       B2M    RPS15A    RPL18A     RPL28   MT-ATP6 
##  1.523138  1.506508  1.433478  1.403471  1.391902  1.296095
## cells retained by counts ( 600 ): 2870 
##  percentage of retained cells: 21.59 %

dir.create("result")
saveRDS(dat, file = "./result/SAMN19314092_clean_QC.Rds")

Feature selection

#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)

Data scaling

Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering

# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data

all.genes <- rownames(dat)

dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))

Dimensionality reduction

dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1 
## Positive:  IGLV2-8, MZB1, P4HB, SEC11C, ITM2C 
## Negative:  HLA-DRA, IGKV3-11, HLA-DPA1, EEF1A1, IGHV3-30 
## PC_ 2 
## Positive:  RPL10, RPLP1, EEF1A1, GAPDH, ACTB 
## Negative:  ITM2C, TXNDC5, CCDC144A, PRPSAP2, IGLC2 
## PC_ 3 
## Positive:  IGLV2-8, PRDX4, CST3, SEC11C, NUCB2 
## Negative:  NEAT1, HLA-DPA1, RGS10, HLA-DRA, HLA-DPB1 
## PC_ 4 
## Positive:  ID2, ID1, NR4A2, EDN1, DDIT4 
## Negative:  PSAT1, TNFRSF17, SELPLG, ACTG1, PHB 
## PC_ 5 
## Positive:  HIST1H2BJ, LINC01480, NME2, HIST2H2AA4, CYTOR 
## Negative:  SELPLG, PSAT1, SCNN1B, SLC1A5, CD200

UMAP

UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:

dat <- FindNeighbors(dat, dims = 1:20)

The graph now can be used as input for the function runUMAP()

dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)

Final plots:

## QC metrics

## markers